Ad execs (and ChatGPT) on AI in marketing: ‘It will create the majority of the work’
AI-powered platforms like ChatGPT, Midjourney and Lensa AI have taken the advertising world by storm in recent months. We asked five experts to respond to the rise of this revolutionary new technology and its potential impacts on the marketing industry. We also asked ChatGPT.
Images created by Midjourney: "An intelligent humanoid machine sitting down at a desk and writing an essay with quill and ink."
Generative AI models – algorithms that create text, images, code and other forms of content based on text-based prompts – entered mainstream consciousness only recently. But some of the most well-known among them have already become immensely popular; it only took five days for ChatGPT, an AI model launched in November which generates text, to reach a million registered users.
Generative AI has become a red-hot topic in adland, presenting both vast new creative possibilities and serious ethical dilemmas. Given the newness and the complexity of the new technology – as well as the considerable amount of hype that has begun to circulate around it – many marketers are likely asking themselves questions such as: ‘Is this a fad?’ ‘Do I need to teach myself how to use these tools?’ ‘To what degree will it reshape my job and my industry?’
We asked marketing experts and ChatGPT to chime in about the current and potential future impacts of generative AI upon the marketing industry:
ChatGPT (responding to the prompt ‘Write 200 words or less about how ChatGPT and other generative AI models like Midjourney are transforming the marketing industry’): “ChatGPT and other generative AI models like Midjourney are transforming the marketing industry by enabling more personalized and efficient communication with customers. These models can be used to generate personalized email and social media content, as well as to assist with customer service interactions. They can also be used to create targeted marketing campaigns by analyzing customer data and identifying patterns and trends.
“Generative AI models can also help with content creation for websites and social media platforms, by writing product descriptions, blog posts and other types of content. Additionally, they can analyze large amounts of data, such as customer reviews and feedback, to identify common issues and concerns, which can help companies improve their products and services.
“Furthermore, AI models can automate repetitive tasks, such as data entry, and free up human workers to focus on more complex and creative tasks. This can lead to cost savings and increased productivity for companies.
“In short, ChatGPT and other generative AI models are helping companies to communicate more effectively with customers, create more personalized and effective marketing campaigns, and improve the overall customer experience. This is the most promising way to increase the efficiency of customer engagement and lead generation.”
John Mescall, global executive creative director, McCann Worldgroup: “I can absolutely envision a world in which the majority of marketing is created by generative AI – and I’m sure there’ll be nothing horribly wrong with the work. The technology will be good enough to do a decent job of mimicking standard human creativity.
“But the very best and most effective work will still be a product of human intelligence, artistry and creativity. Because when everyone has access to the same technology, the only way to truly create something unique will be to employ human minds that are capable of seeing, thinking and strategizing beyond the norms.
“I predict that technology will eventually replace all but the most creative and nuanced of tasks. Hopefully, this is a nudge to us all. Creativity has always been – and always will be – our most essential currency.”
James Huerta, executive director of creative technology, Havas CX: “2022 was the year that creative applications of AI went mainstream. Even your luddite uncle has read about ChatGPT and knows it by name or has played with Lensa AI and wants to show you his movie posters. There are two good reasons for this shift: first, these systems are finally capable of generating words, imagery and art that feel credibly human and not like a canned Q&A bot or someone’s dystopian nightmare; second, they are widely accessible on the web and apps with intuitive interfaces that make playing with AI and seeing immediate results – something that almost anyone can do.
“Within a marketing context, these advances deliver a lot of power for brands to be able to generate large amounts of personalized messaging and content. As more of these services are available on the web via application programming interfaces (APIs), embedding ‘AI-on-the-fly’ could become as easy as setting up a Squarespace site.
“But let’s not get ahead of ourselves. The biggest challenges around ethics, attribution and, most importantly, facts have not been solved. We’re currently in the stage of what could be called ‘plausible content,’ which looks great at a glance, but if the system is inventing facts or images, we’ve created something dangerous. Humans will need to supervise this closely for the foreseeable future and remain accountable for its impacts. And for an industry like ours, I’d suggest that creative work that is ‘plausibly good’ to the untrained eye creates more potential harm than work that is obviously bad.”
Suggested newsletters for you
Mansoor Basha, chief technology officer, Stagwell Marketing Cloud: “Artificial intelligence and machine learning are at the forefront of digital transformation across industries and will undoubtedly remain there for the foreseeable future. In a 2011 op-ed, Marc Andreessen observed an environment in which software was increasingly becoming king, famously stating that ‘software is eating the world.’ His observation came about a decade after the peak of the 1990s dot-com bubble as companies like Facebook and Skype were booming. Looking to the next decade, I believe that AI and machine learning will be eating the world, changing the way we work, live and interact with brands.
“I predict that as AI technology continues to change everything around us, consumers will have more time to be engaged through new forms of media. This will give brands the opportunity to leverage more pointed advertising to reach their audiences. AI will find brands’ ideal consumers and reach them in the right place at the right time, especially as augmented reality and virtual reality inch further into mainstream culture. And as the hype around generative AI simmers down, marketing teams will become more comfortable adopting a wide range of AI tools that can help them build powerful workflows that drive innovation, aid in decision making and create new business models.
“Overall, generative AI will be an entry point for many marketing teams as they look for relevant ways to use new technologies in their day-to-day work. The future of marketing will be more precise and more focused, and it will see much higher levels of engagement.”
Aaron Kwittken, founder and chief executive officer, PRophet: “Generative AI, while not perfect, is the needle that pierced the veil of doubt and fear among marketers when it comes to adopting AI technology. The current limitations are only the result of a lack of data.
“When paired with the right inputs, this technology will make marketers more efficient by enabling them to create base content faster and better, and freeing them up for higher value tasks like editing and strategy deployment. In addition to assisting with content creation for press releases, social posts, pitches, marketing collateral, blogs and other text-based materials, this technology can be a huge aid with legal and compliance issues, especially when working with third parties like influencers and celebrity spokespeople.
“But make no mistake – the downsides will need to be managed.
“Generative AI may reduce the need for some junior staff members; it could be used to create and spread misinformation and disinformation; and it could make professionals more complacent, less creative and more transactional. The responsibility will fall on marketers to figure out how they’ll use this new technology to enhance their current activities, rather than simply replacing them.”
Ben Williams, global chief creative experience officer, TBWA Worldwide: “Generative AI models are making their way into mainstream creative processes as valid and powerful tools to fast-track the creation of imagery, text, videos and other assets. Its real power is accelerating the manifestation of a thought or an idea – a radical departure from when visualizing or writing a concept could take hours or even days.
“But while these tools are helpful, human involvement in the creative process is still essential. These tools are exactly that: tools. As they develop we'll still need humans to apply their discerning eyes and decide what works from a creative perspective. We need humans to identify and flag any biases or falsities in the content the AI models create. And when we’re using these tools to create content for a brand, we need humans to ensure that such content aligns with that brand's broader values and messaging.
“We need to tap into the power of these tools to explore the possibilities and supercharge creativity across the board. Let’s just remember that we, as humans, are still very much needed.”
For more on the latest happening in tech, sign up for The Drum’s Inside the Metaverse weekly newsletter here.